CVE-2026-31951

MEDIUM

6.8

Description

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containing `{{LIBRECHAT_OPENID_ACCESS_TOKEN}}` (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue.

CVE Details

CVSS v3.1 Score6.8

SeverityMEDIUM

CVSS VectorCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredLOW

User InteractionREQUIRED

Published3/27/2026

Last Modified3/30/2026

Sourcenvd

Honeypot Sightings0

Affected Products

librechat:librechat

Weaknesses (CWE)

CWE-200

References

https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.